Redis
PulseAugur coverage of Redis — every cluster mentioning Redis across labs, papers, and developer communities, ranked by signal.
- developed by Salvatore Sanfilippo 100%
- founded by Salvatore Sanfilippo 90%
- founded Salvatore Sanfilippo 90%
- used by BullMQ 70%
- used by nginx 70%
- authored Salvatore Sanfilippo 70%
- used by Bifröst 70%
- developed Salvatore Sanfilippo 70%
- used by Vercel AI SDK 70%
- used by NestJS 70%
- used by Upstash 70%
- used by Docker 60%
28 day(s) with sentiment data
-
Dida Travel exec shares 14 years of engineering lessons learned
A former executive at Dida Travel shared engineering lessons learned over 14 years of building the company, which grew to process over $12 billion in bookings annually. The company's initial mistake was building too man…
-
Vector search struggles with negation and exact identifiers
Vector search models struggle to differentiate between positive and negative statements regarding specific entities, such as services using Redis versus those that do not. This limitation stems from the models encoding …
-
Production LLM Apps Need MLOps: Tools and Infrastructure Detailed
Building a production-ready LLM application requires more than just a functional model; it involves a robust MLOps infrastructure. Key components include model deployment tools like Amazon SageMaker and Databricks, orch…
-
Redis Creator Develops Open-Source H3 Inference Engine for Mac
Salvatore Sanfilippo, the creator of Redis, has developed an open-source inference engine for MiniMax AI's H3 model, optimized for Mac computers using Metal. This implementation allows for broad accessibility and modifi…
-
Shopify scales inventory reservations by switching from Redis to MySQL
Shopify has successfully transitioned its inventory reservation system from Redis to MySQL. This change was implemented to improve scalability and performance for handling a high volume of inventory reservations. The co…
-
Feature stores solve ML training-serving drift and target leakage
Feature stores are essential for production machine learning, addressing the critical problem of feature definition drift between training and serving environments. This drift can silently degrade model performance, par…
-
AI app developer optimizes LLM concurrency with Redis-backed tier-aware queueing
A developer details how they improved their AI companion app's performance by implementing a tier-aware queueing system for LLM requests. The initial approach using a global asyncio.Semaphore led to free-tier users caus…
-
Open-source Dify platform simplifies LLM app development and deployment
This guide details the deployment of Dify, an open-source platform for building LLM applications. It covers setting up Dify using Docker Compose, configuring a domain with Let's Encrypt for secure HTTPS access, and conn…
-
LLMs need commit history, not just final code, to become real engineers
Current large language models trained on GitHub code are excellent imitators but lack true engineering understanding because they only see final code versions. The author proposes training LLMs on the full commit histor…
-
Guide: How to Write Effective CLAUDE.md Files for Claude Code
This article provides a guide on how to effectively use CLAUDE.md files to instruct Claude Code, an AI coding assistant. It highlights common mistakes such as writing vague philosophical statements instead of actionable…
-
Ragleap launches RAG library with focus on narrow scope
Ragleap has launched its RAG library, emphasizing a deliberate focus on narrow scope rather than broad feature parity. The library prioritizes retrieval-augmented generation, explicitly excluding agentic tool-calling an…
-
CLAUDE.md vs. Memory MCP: Choosing the Right AI Agent Fact Storage
This article distinguishes between CLAUDE.md files and memory MCP servers for AI agents, explaining when each is appropriate. CLAUDE.md is suitable for stable, human-curated facts about a project, such as build commands…
-
Modal cuts serverless function latency with new distributed I/O plane
Modal has upgraded its serverless functions' I/O plane to reduce network latency. The new system routes function inputs and outputs through geographically distributed regions, rather than a single central server. This c…
-
Claude Code introduces ExitPlanMode for explicit user approval of AI plans
Anthropic's Claude Code has introduced a new tool called ExitPlanMode, designed to streamline the AI's planning and execution workflow. This tool specifically addresses the need for explicit user approval before Claude …
-
Langchain-Rust framework enables LLM apps in pure Rust, bypassing Python
The langchain-rust library offers a comprehensive framework for building LLM applications entirely in Rust, eliminating the need for Python. It provides first-class integration with Ollama for local models, supporting f…
-
Build a semantic cache for LLM apps to cut costs
A technical guide demonstrates how to build a semantic cache for LLM applications using Python, aiming to reduce API call costs. The approach involves converting user queries into vector embeddings using SentenceTransfo…
-
Pydantic AI v2 integrated into production systems to improve LLM output reliability
Pydantic AI v2 is being integrated into three specific areas within existing production systems, focusing on improving the reliability of LLM outputs. Instead of replacing the current LangGraph orchestration framework, …
-
AI Agents' Retries Can Cost Thousands Annually Due to Lack of Idempotency
AI agents can incur significant costs due to unhandled retries, potentially costing enterprises thousands of dollars annually. This issue arises because LLM applications often lack proper idempotency, meaning repeated r…
-
Nous Research integrates Hermes Agent with Buzz workspace
Nous Research has introduced three integration methods for its Hermes Agent with Buzz, an open-source workspace designed for both humans and AI agents. Buzz, built on the Nostr protocol, allows agents to have their own …
-
Model Context Protocol updates to stateless requests with explicit state handles
The Model Context Protocol (MCP) has been updated to remove protocol-level sessions, requiring requests to be self-describing. This change, effective July 28, 2026, aims to improve scalability by allowing requests to be…